Rockburst Intensity Grade Prediction Model Based on Batch Gradient Descent and Multi-Scale Residual Deep Neural Network

Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and tunnels.Light rockburst only peels off rock slices without ejection,while severe rockburst causes casualties and property loss.The frequency and degree of rockburst damage increases with the excavation depth.Moreover,rockburst is the leading engineering geological hazard in the excavation process,and thus the prediction of its intensity grade is of great significance to the development of geotechnical engineering.Therefore,the prediction of rockburst intensity grade is one problem that needs to be solved urgently.By comprehensively considering the occurrence mechanism of rockburst,this paper selects the stress index(σθ/σc),brittleness index(σ_(c)/σ_(t)),and rock elastic energy index(Wet)as the rockburst evaluation indexes through the Spearman coefficient method.This overcomes the low accuracy problem of a single evaluation index prediction method.Following this,the BGD-MSR-DNN rockburst intensity grade prediction model based on batch gradient descent and a multi-scale residual deep neural network is proposed.The batch gradient descent(BGD)module is used to replace the gradient descent algorithm,which effectively improves the efficiency of the network and reduces the model training time.Moreover,the multi-scale residual(MSR)module solves the problem of network degradation when there are too many hidden layers of the deep neural network(DNN),thus improving the model prediction accuracy.The experimental results reveal the BGDMSR-DNN model accuracy to reach 97.1%,outperforming other comparable models.Finally,actual projects such as Qinling Tunnel and Daxiangling Tunnel,reached an accuracy of 100%.The model can be applied in mines and tunnel engineering to realize the accurate and rapid prediction of rockburst intensity grade.

Ash Detection of Coal Slime Flotation Tailings Based on Chromatographic Filter Paper Sampling and Multi-Scale Residual Network

The detection of ash content in coal slime flotation tailings using deep learning can be hindered by various factors such as foam,impurities,and changing lighting conditions that disrupt the collection of tailings images.To address this challenge,we present a method for ash content detection in coal slime flotation tailings.This method utilizes chromatographic filter paper sampling and a multi-scale residual network,which we refer to as MRCN.Initially,tailings are sampled using chromatographic filter paper to obtain static tailings images,effectively isolating interference factors at the flotation site.Subsequently,the MRCN,consisting of a multi-scale residual network,is employed to extract image features and compute ash content.Within the MRCN structure,tailings images undergo convolution operations through two parallel branches that utilize convolution kernels of different sizes,enabling the extraction of image features at various scales and capturing a more comprehensive representation of the ash content information.Furthermore,a channel attention mechanism is integrated to enhance the performance of the model.The combination of the multi-scale residual structure and the channel attention mechanism within MRCN results in robust capabilities for image feature extraction and ash content detection.Comparative experiments demonstrate that this proposed approach,based on chromatographic filter paper sampling and the multi-scale residual network,exhibits significantly superior performance in the detection of ash content in coal slime flotation tailings.

MRI Brain Tumor Segmentation Using 3D U-Net with Dense Encoder Blocks and Residual Decoder Blocks

The main task of magnetic resonance imaging (MRI) automatic brain tumor segmentation is to automaticallysegment the brain tumor edema, peritumoral edema, endoscopic core, enhancing tumor core and nonenhancingtumor core from 3D MR images. Because the location, size, shape and intensity of brain tumors vary greatly, itis very difficult to segment these brain tumor regions automatically. In this paper, by combining the advantagesof DenseNet and ResNet, we proposed a new 3D U-Net with dense encoder blocks and residual decoder blocks.We used dense blocks in the encoder part and residual blocks in the decoder part. The number of output featuremaps increases with the network layers in contracting path of encoder, which is consistent with the characteristicsof dense blocks. Using dense blocks can decrease the number of network parameters, deepen network layers,strengthen feature propagation, alleviate vanishing-gradient and enlarge receptive fields. The residual blockswere used in the decoder to replace the convolution neural block of original U-Net, which made the networkperformance better. Our proposed approach was trained and validated on the BraTS2019 training and validationdata set. We obtained dice scores of 0.901, 0.815 and 0.766 for whole tumor, tumor core and enhancing tumorcore respectively on the BraTS2019 validation data set. Our method has the better performance than the original3D U-Net. The results of our experiment demonstrate that compared with some state-of-the-art methods, ourapproach is a competitive automatic brain tumor segmentation method.

Underwater Image Enhancement Based on Multi-scale Adversarial Network

In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.

Abnormal Traffic Detection for Internet of Things Based on an Improved Residual Network

Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.

Ghost Module Based Residual Mixture of Self-Attention and Convolution for Online Signature Verification

Online Signature Verification (OSV), as a personal identification technology, is widely used in various industries.However, it faces challenges, such as incomplete feature extraction, low accuracy, and computational heaviness. Toaddress these issues, we propose a novel approach for online signature verification, using a one-dimensionalGhost-ACmix Residual Network (1D-ACGRNet), which is a Ghost-ACmix Residual Network that combines convolutionwith a self-attention mechanism and performs improvement by using Ghost method. The Ghost-ACmix Residualstructure is introduced to leverage both self-attention and convolution mechanisms for capturing global featureinformation and extracting local information, effectively complementing whole and local signature features andmitigating the problem of insufficient feature extraction. Then, the Ghost-based Convolution and Self-Attention(ACG) block is proposed to simplify the common parts between convolution and self-attention using the Ghostmodule and employ feature transformation to obtain intermediate features, thus reducing computational costs.Additionally, feature selection is performed using the random forestmethod, and the data is dimensionally reducedusing Principal Component Analysis (PCA). Finally, tests are implemented on the MCYT-100 datasets and theSVC-2004 Task2 datasets, and the equal error rates (EERs) for small-sample training using five genuine andforged signatures are 3.07% and 4.17%, respectively. The EERs for training with ten genuine and forged signaturesare 0.91% and 2.12% on the respective datasets. The experimental results illustrate that the proposed approacheffectively enhances the accuracy of online signature verification.

Multi-scale Attention Dilated Residual Image Denoising Network Based on Skip Connection

In the field of image denoising, deep learning technology holds a dominance. However, the current network model tends to lose fine-grained information with the depth of the network. To address this issue, this paper proposes a Multi-scale Attention Dilated Residual Image Denoising Network(MADRNet) based on skip connection, which consists of Dense Interval Transmission Block(DTB), Sparse Residual Block(SRB), Dilated Residual Attention Reconstruction Block(DRAB) and Noise Extraction Block(NEB). The DTB enhances the classical dense layer by reducing information redundancy and extracting more accurate feature information. Meanwhile, SRB improves feature information exchange and model generalization through the use of sparse mechanism and skip connection strategy with different expansion factors. The NEB is primarily responsible for extracting and estimating noise. Its output, together with that of the sparse residual module, acts on the DRAB to effectively prevent loss of shallow feature information and improve denoising effect. Furthermore, the DRAB integrates an dilated residual block into an attention mechanism to extract hidden noise information while using residual learning technology to reconstruct clear images. We respectively examined the performance of MADRNet in gray image denoising, color image denoising and real image denoising. The experiment results demonstrate that proposed network outperforms some excellent image denoising network in terms of peak signal-to-noise ratio, structural similarity index measurement and denoising time. The proposed network effectively addresses issues associated with the loss of detail information.

Disease Recognition of Apple Leaf Using Lightweight Multi-Scale Network with ECANet

To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.

Speech Enhancement via Residual Dense Generative Adversarial Network

Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent years.Various GANbased enhancement methods are presented to improve the quality of reconstructed speech.However,the performance of these GAN-based methods is worse than those of masking-based methods.To tackle this problem,we propose speech enhancement method with a residual dense generative adversarial network(RDGAN)contributing to map the log-power spectrum(LPS)of degraded speech to the clean one.In detail,a residual dense block(RDB)architecture is designed to better estimate the LPS of clean speech,which can extract rich local features of LPS through densely connected convolution layers.Meanwhile,sequential RDB connections are incorporated on various scales of LPS.It significantly increases the feature learning flexibility and robustness in the time-frequency domain.Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments.Specifically,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes.It indicates that our method is more generalized in untrained conditions.

An Efficient Steganalysis Model Based on Multi-Scale LTP and Derivative Filters

Local binary pattern(LBP)is one of the most advanced image classification recognition operators and is commonly used in texture detection area.Research indicates that LBP also has a good application prospect in steganalysis.However,the existing LBP-based steganalysis algorithms are only capable to detect the least significant bit(LSB)and the least significant bit matching(LSBM)algorithms.To solve this problem,this paper proposes a steganalysis model called msdeLTP,which is based on multi-scale local ternary patterns(LTP)and derivative filters.The main characteristics of the msdeLTP are as follows:First,to reduce the interference of image content on features,the msdeLTP uses derivative filters to acquire residual images on which subsequent operations are based.Second,instead of LBP features,LTP features are extracted considering that the LTP feature can exhibit multiple variations in the relationship of adjacent pixels.Third,LTP features with multiple scales and modes are combined to show the relationship of neighbor pixels within different radius and along different directions.Analysis and simulation show that the msdeLTP uses only 2592-dimensional features and has similar detection accuracy as the spatial rich model(SRM)at the same time,showing the high steganalysis efficiency of the method.

Grinding/Cutting Technology and Equipment of Multi-scale Casting Parts

Multi-scale casting parts are important components of high-end equipment used in the aerospace,automobile manufacturing,shipbuilding,and other industries.Residual features such as parting lines and pouring risers that inevitably appear during the casting process are random in size,morphology,and distribution.The traditional manual processing method has disadvantages such as low efficiency,high labor intensity,and harsh working environment.Existing machine tool and serial robot grinding/cutting equipment do not easily achieve high-quality and high-efficiency removal of residual features due to poor dexterity and low stiffness,respectively.To address these problems,a five-degree-of-freedom(5-DoF)hybrid grinding/cutting robot with high dexterity and high stiffness is proposed.Based on it,three types of grinding/cutting equipment combined with offline programming,master-slave control,and other technologies are developed to remove the residual features of small,medium,and large casting parts.Finally,the advantages of teleoperation processing and other solutions are elaborated,and the difficulties and challenges are discussed.This paper reviews the grinding/cutting technology and equipment of casting parts and provides a reference for the research on the processing of multi-scale casting parts.

An Experimental Study on the Use of Fonio Straw and Shea Butter Residue for Improving the Thermophysical and Mechanical Properties of Compressed Earth Blocks

The efficient use of building materials is one of the responses to increasing urbanization and building energy consumption. Soil as a building material has been used for several thousand years due to its availability and its usual properties improving and stabilization techniques used. Thus, fonio straws and shea butter residues are incorporated into tow soil matrix. The objective of this study is to develop a construction eco-material by recycling agricultural and biopolymer by-products in compressed earth blocks (CEB) stabilization and analyze these by-products’ influence on CEB usual properties. To do this, compressed stabilized earth blocks (CSEB) composed of clay and varying proportion (3% to 10%) of fonio straw and shea butter residue incorporated were subjected to thermophysical, flexural, compressive, and durability tests. The results obtained show that the addition of fonio straw and shea butter residues as stabilizers improves compressed stabilized earth blocks thermophysical and mechanical performance and durability. Two different clay materials were studied. Indeed, for these CEB incorporating 3% fonio straw and 3% - 10% shea butter residue, the average compressive strength and three-point bending strength values after 28 days old are respectively 3.478 MPa and 1.062 MPa. In terms of CSEB thermal properties, the average thermal conductivity is 0.549 W/m·K with 3% fonio straw and from 0.667 to 0.798 W/m. K is with 3% - 10% shea butter residue and the average thermal diffusivity is 1.665.10-7 m2/s with 3% FF and 2.24.10-7 m2/s with 3.055.10-7 m2/s with 3% - 10% shea butter residue, while the average specific heat mass is between 1.508 and 1.584 kJ/kg·K. In addition, the shea butter residue incorporated at 3% - 10% improves CSEB water repellency, with capillary coefficient values between 31 and 68 [g/m2·s]1/2 and a contact angle between 43.63°C and 86.4°C. Analysis of the results shows that, it is possible to use these CSEB for single-storey housing construction.

Speech Enhancement via Mask-Mapping Based Residual Dense Network

Masking-based and spectrum mapping-based methods are the two main algorithms of speech enhancement with deep neural network(DNN).But the mapping-based methods only utilizes the phase of noisy speech,which limits the upper bound of speech enhancement performance.Maskingbased methods need to accurately estimate the masking which is still the key problem.Combining the advantages of above two types of methods,this paper proposes the speech enhancement algorithm MM-RDN(maskingmapping residual dense network)based on masking-mapping(MM)and residual dense network(RDN).Using the logarithmic power spectrogram(LPS)of consecutive frames,MM estimates the ideal ratio masking(IRM)matrix of consecutive frames.RDN can make full use of feature maps of all layers.Meanwhile,using the global residual learning to combine the shallow features and deep features,RDN obtains the global dense features from the LPS,thereby improves estimated accuracy of the IRM matrix.Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments.Specifically,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,MM-RDN can still outperform the existing convolutional recurrent network(CRN)method in themeasures of perceptual evaluation of speech quality(PESQ)and other evaluation indexes.It indicates that the proposed algorithm is more generalized in untrained conditions.

Analysis of incidence of residue neuromuscular blockade for rocuronium and cisatracurium

Objective:To observe the incidence of residual neuromuscular blockade at the end of operation and during tracheal extubation, and analyze the risk factors causing residual neuromuscular blockade by judging the degree of muscle relaxation according to clinical signs when after using rocuronium or cis-atracurium in general anesthesia.Methods: 500 adults were implemented with propofol-remifentanil intravenous anesthesia or sevoflurane inhalation anesthesia. Rocuronium and cis-atracurium were given, respectively. The TOFr was observed with blind method by TOF Watch SX monitor during anesthesia.Results: The mean TOFr=0.53±0.38 at the end of operation,including 275 cases of 0<TOFr<0.9 and 112 cases of TOFr=0. The mean TOFr=0.97±0.12 at extubation, including 60 cases of TOFr<0.9. The incidence of residual neuromuscular blockade at extubation showed an increasing trend with the increase of age or body mass index. The average TOFr value at extubation, which interval time over 10 min after neostigmine administration to extubation was significant higher than that of interval time less than 10 min.Conclusions:There has 12% patients with TOFr<0.9 when extubation by estimating rocuronium and cis-atracurium effect with clinical signs and experience, it has a hidden danger of residual neuromuscular blockade. The main risk factors to increasing the incidence of residual neuromuscular blockade are growing old and the short time of administrating muscle relaxants or neostigmine to extubation.

Portland Cement-Residues-Polymers Composites and Its Application to the Hollow Blocks Manufacturing

Agricultural wastes and sawdust combined with cement matrix in the manufacture of building elements has been practiced with success in developed countries. In this study, sawdust from wood species (Pinus caribaea and Eucalyptus grandis) and an agricultural waste—rice husk (Oriza sativa) were combined with Portland cement type V (high initial strength), modified by polymer styrene-butadiene (SBR) addition. Hollow blocks produced with Eucalyptus grandis and rice husk residues showed better compressive strength;however, those produced with residues derived from Pinus caribaea presented non-satisfactory results, due to the particle size that was used.

Grasp Detection with Hierarchical Multi-Scale Feature Fusion and Inverted Shuffle Residual

Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are neglected.It is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains unsolved.Meanwhile,the channel information in high-level feature is also not well mined.Inevitably,the performance of grasp detection is degraded.To solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle residual.Both low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature fusion.Such a hierarchical fusion guarantees the quality of grasp prediction.Furthermore,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective branches.By such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the network.Besides,an information enhancement module is added before the encoder to reinforce input information.The proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.

Analysis of synergistic influence of multi-scale design parameters on nearly-zero energy office blocks performance based on architectural morphological classification and parametric modeling

Design parameters at different scales in the pre-design phase could significantly impact both building energy consumption and photovoltaic(PV)power generation potential.However,existing studies often overlook the synergistic effects of design parameters across multiple scales(block-building-facade scales)when evaluating these aspects.This paper aims to propose a workflow for the assessing building energy consumption and PV power generation potential of office blocks applicable in the pre-schematic design phase considering the synergistic influence of multi-scale design parameters,using building typology and parametric modelling approach.The study proposed a multi-scale design parameter classification system combined with parametric modelling.The study investigated 80 office blocks in Wuhan as the study case,which were classified into array type and enclosed type.Correlation analysis and multiple regression equations were used to quantify the single versus synergistic effects of different scale design parameters.Results suggest that focusing solely on a single scale during the pre-design stage is typically inadequate for understanding building energy potential.In contrast,multi-scale synergistic analysis boosts energy use intensity(EUI)by 7.56%and net energy use intensity(NEUI)by 33.96%.Under multi-scale synergistic conditions,the EUI of array type is more influenced by the building design parameters,while the NEUI is effected by the balance of multi-scales design parameters.While the EUI of enclosed types exhibit balanced effects across multi-scale design parameters,with NEUI results aligning closely with PV power generation potential.Multiple regression equations highlight building density and shape factor as key influencers for both array and enclosure layouts.This study offers designers a flexible and scalable workflow for evaluating building energy consumption and PV power generation potential in the pre-design phase.The findings can guide nearly-zero energy urban block planning to achieve a balance between energy supply and demand.

Comparative Study of Thermal Comfort Induced from Masonry Made of Stabilized Compressed Earth Block vs Conventional Cementitious Material

This paper investigates the stabilization effect on compressed earth blocks (CEB) produced from quartz-kaolinite rich earthen material stabilized with 0% - 25% calcium carbide residue (CCR). The paper evaluated various physico-thermal properties of the stabilized CEB and thermal comfort in the model building made of CEB masonry. The optical properties of CEB were evaluated from the mineral composition of the earthen material and CCR and apparent density of the CEB. A simulation was carried out on naturally ventilated model building whose masonry is made of CCR stabilized CEB comparing to the so-called conventional cementitious materials such as cement blocks and concrete. The results showed a decrease of the apparent density of the CEB from 2100 kg·m&ndash;3 for unstabilized CEB (0% CCR) to 1600 kg·m&ndash;3 for 25% CCR stabilized CEB. The thermal conductivity and depth of penetration of the heat flux on a 24 hours period of CEB respectively decreased from 1 W·m&ndash;1·K&ndash;1 and 12.7 cm for 0% CCR-CEB to 0.5 W·m&ndash;1·K&ndash;1 and 10.2 cm for 25% CCR-CEB. The emissivity, solar absorptivity and visible absorptivity of the CEB respectively decreased from 0.82, 0.82 and 0.82 for 0% CCR-CEB to 0.80, 0.64 and 0.64 for 25% CCR-CEB. The number of hours of warm and humid thermal discomfort was impacted for stabilized CEB based masonry in comparison with cement based masonry. The warm discomfort in building made of 20% CCR-CEB masonry was 400 hours lesser than that in building made of hollow cement blocks masonry. If air conditioning system is used to keep the indoor temperature below 28°C, the economy of 310,000 CFA francs (535 USD) is made every year on energy consumption for cooling in the model building made of 20% CCR-CEB masonry, corresponding to 9.6% less, with respect to that made of hollow cement blocks masonry.

Designing Pair of Nonlinear Components of a Block Cipher over Gaussian Integers

In block ciphers,the nonlinear components,also known as sub-stitution boxes(S-boxes),are used with the purpose of inducing confusion in cryptosystems.For the last decade,most of the work on designing S-boxes over the points of elliptic curves has been published.The main purpose of these studies is to hide data and improve the security levels of crypto algorithms.In this work,we design pair of nonlinear components of a block cipher over the residue class of Gaussian integers(GI).The fascinating features of this structure provide S-boxes pair at a time by fixing three parameters.But the prime field dependent on the Elliptic curve(EC)provides one S-box at a time by fixing three parameters a,b,and p.The newly designed pair of S-boxes are assessed by various tests like nonlinearity,bit independence criterion,strict avalanche criterion,linear approximation probability,and differential approximation probability.

CIRBlock:融合低代价卷积的轻量反向残差模块

针对轻量级卷积神经网络MobileNet采用的反向残差结构仍具有较多的冗余计算的问题,构建了一种更为轻量的反向残差模块(cheap inverted residuals block,CIRBlock),并设计了一种新的轻量级卷积神经网络CIRNet。通过低代价卷积操作,简化逐点卷积,并构建旁路分支进行特征复用,减少反向残差的输出通道;利用通道注意力机制和通道混洗,增强通道间信息交流;在下采样时利用旁路分支信息构建和主分支相同的拓扑结构,提高特征冗余结构的通道多样性;完成轻量化网络模块CIRBlock的设计,并通过人工堆叠CIRBlock构建不同复杂度的轻量级卷积神经网络CIRNet。在目标分类上的实验表明:在CIFAR数据集上,基于相同的VGG16架构,使用CIRBlock比使用MobileNetV2的反向残差结构FLOPs降低58.1%,参数量减少55.5%,分类精度损失小于0.4%。在Mini-ImageNet目标分类数据集上,CIRNet分类精度比MobileNetV2高0.35%,FLOPs降低69%,参数量减少77.4%。